2.2.1 Spotting the Typo

dat %>% group_by(maturity) %>% summarise(n = n()) %>% 
    kbl(align = "l", format.args = list(big.mark = ",")) %>% 
    kable_styling(
        full_width = F,
        bootstrap_options = c("hover", "responsive", "striped"))

2.2.2 Fix with Case When

dat <- dat %>% 
    mutate( #tidying text and a typo in the data
        name_scientific = name_scientific %>% str_to_title(),
        maturity = case_when(maturity == "Adut" ~ "Adult",
                             T ~ maturity),
        name_scientific = case_when(name_scientific == "Saintpaulia" ~ "Saintpaulia Incognita",
                                    T ~ name_scientific))

2.3.1 Engineering Genus

dat <- dat %>% 
    separate(col = name_scientific, 
             into = c("genus"), 
             sep = " ", 
             remove = FALSE) %>% #pulling the genus out of the scientific genus species
    select(genus, contains("name"), water, maturity, id) %>% 
    mutate(genus = genus %>% as_factor(),
           name_common = name_common %>% str_to_title()) 

## Warning: Expected 1 pieces. Additional pieces discarded in 73 rows [1, 2, 3, 4,
## 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, ...].

dat %>% distinct(genus) %>% pull()

##  [1] Ficus         Musa          Alocasia      Pilea         Maranta      
##  [6] Anthurium     Monstera      Begonia       Epiprenem     Peperomia    
## [11] Philodendron  Saintpaulia   Scindapsus    Ludisia       Ceropegia    
## [16] Rhaphidophora Macodes       Calathea      Oxalis        Zamioculcas  
## [21] Aeschynanthus Adenium      
## 22 Levels: Ficus Musa Alocasia Pilea Maranta Anthurium Monstera ... Adenium

2.3.2 Engineering Species

dat <- dat %>% 
    mutate(species = str_remove(as.character(name_scientific), 
                                as.character(genus)) %>% 
               trimws("both")) %>% #using genus to derive species from scientific name
    select(genus, species, contains("name"), maturity, water, id)

dat %>% distinct(species) %>% pull()

##  [1] "Benghalensis"               "Acuminata"                 
##  [3] "Odora Variegata"            "Elastica 'Tineke'"         
##  [5] "Lyrata"                     "Peperomiodes"              
##  [7] "Leuconeura 'Kerchoviana'"   "Regale"                    
##  [9] "Deliciosa 'Albo Variegata'" "'Lois Burke'"              
## [11] "Maculata"                   "Aurem"                     
## [13] "Leuconeura 'Red'"           "Elastica 'Ruby'"           
## [15] "Leuconeura 'Lemon Lime'"    "Obtusifolia"               
## [17] "Verrucosum 'Mini'"          "Incognita"                 
## [19] "Adansonii"                  "'El Choco'"                
## [21] "Pictus 'Argyraeus'"         "Clarinervium"              
## [23] "Dorayaki"                   "Crystallinum"              
## [25] "Regale+Magnificum"          "Magnificum"                
## [27] "Discolor"                   "Erubescens"                
## [29] "Woodii Variegata"           "Pictus 'Silver Lady'"      
## [31] "Prostrata"                  "Micans"                    
## [33] "Tetrasperma"                "Petola"                    
## [35] "Cadieri"                    "Makoyana"                  
## [37] "Verrucosum X Melanochrysum" "Ornata"                    
## [39] "Regnelli"                   "Deliciosa"                 
## [41] "'Regal Shields'"            "Elastica 'Burgundy'"       
## [43] "Woodii"                     "Zamiifoli"                 
## [45] "Longicaulis"                "‘Swan And Dragon’"         
## [47] "Fibrous 'My Special Angel'" "Fibrous 'Whimsy'"          
## [49] "Verrucosum"

3.3.1 Top 5 Genera

To start, I’m honing in on the top 5 genera within my collection. The generan selected are: Anthurium, Ficus, Monstera, Begonia, & Philodendron.

I call this visualization Life in a Lock as a saw a parallel between the visualization and that of a keyhole. “Life” stemming from how the visualization depicts biodiversity within my collection.

# library
library(tidyverse)
 
# Create dataset
data <- plant_dat %>% filter(n_genus >= 5) %>% 
    group_by(genus, name_scientific, species) %>% 
    summarise(n = n()) %>% ungroup()

## `summarise()` has grouped output by 'genus', 'name_scientific'. You can override
## using the `.groups` argument.

  data$genus <- factor(data$genus, 
         levels = c("Anthurium", 
                    "Ficus",
                    "Monstera",
                    "Begonia",
                    "Philodendron")) 
  
   data$species <- factor(data$species,
                levels = c("Clarinervium","Crystallinum",
                           "Magnificum","Regale",
                           "Dorayaki","Regale+Magnificum", 
                           "Lyrata","Elastica 'Ruby'" ,
                           "Benghalensis","Elastica 'Tineke'",
                           "Elastica 'Burgundy'",
                           "Deliciosa 'Albo Variegata'",
                           "Deliciosa",
                           "Adansonii","Maculata", 
                           "'Lois Burke'","Fibrous 'My Special Angel'",
                           "Fibrous 'Whimsy'","Verrucosum 'Mini'",
                           "'El Choco'","Erubescens",
                           "Micans","Verrucosum X Melanochrysum",
                           "Verrucosum"))
      
data <- data %>% 
      mutate(group = genus,
             individual = species,
             value = n) %>% 
      select(group, individual, value)



# Set a number of 'empty bar' to add at the end of each group
empty_bar <- 4
to_add <- data.frame( matrix(NA, empty_bar*nlevels(data$group), ncol(data)) )
colnames(to_add) <- colnames(data)
to_add$group <- rep(levels(data$group), each=empty_bar)
data <- rbind(data, to_add)
data <- data %>% arrange(group)
data$id <- seq(1, nrow(data))
# 
# label_data <- data
# number_of_bar <- nrow(label_data)
# label_data$angle <- 360 * (label_data$id-0.5)/number_of_bar     # I substract 0.5 because the letter must have the angle of the center of the bars. Not extreme right(1) or extreme left (0)
# # label_data$hjust <- ifelse(angle < -90, 1, 0)
# # label_data$angle <- ifelse(angle < -90, angle+180, angle)
 
# Make the plot
p <- ggplot(data, aes(x=individual, y=value, fill = group)) +  
  geom_bar(stat="identity") +
  ylim(-1,5) +
  scale_fill_viridis_d(option = "plasma", direction = 1) +
  theme_ipsum() +
    labs(
        title = "Life in a Lock",
        subtitle = "Biodiversity amongst my top Genera",
        caption = "Out of the 22 Genera represented, my top 5 represent 47.5% of my collection",
        x = "",
        y = "Count",
        fill = "Genera") +
    theme(
      legend.position = "bottom",
#     axis.text = element_blank(),
#     axis.text.x = element_text(angle = 90),
#     axis.title = element_blank(),
#      panel.grid = element_blank(),
     plot.margin = margin(.5, .5, .5, .5, "cm")
)  +
  coord_polar(start = 3.05, clip = "off")
    

 
p

## Warning: Removed 20 rows containing missing values (position_stack).